Lunge documentation

An agent-native advanced API client - execute and test REST, GraphQL, WebSocket, SSE, and (later) gRPC requests from any MCP-capable AI agent. No GUI, no manual clicking, no heavyweight desktop app. Think advanced curl, native for agents.

Lunge is a lightweight, token-efficient alternative to Postman and Bruno for the era of AI coding agents. The agent calls tools directly over stdio; there are no humans in the loop and no bloated feature surface to pay for. A Rust core handles execution, protocols, and summarization, exposed to a thin TypeScript MCP layer via napi-rs.

What you'll find here

• Install - set up the Lunge MCP server in Cursor, Windsurf, or Claude Desktop.
• Quick start - fire your first request, chain a token, and inspect a response.
• MCP tools - the full tool surface: names, inputs, outputs, and examples.
• Architecture - the Rust/TS split, module layout, streaming strategy, and the FFI boundary.
• Collections - the declarative YAML/JSON test/collection format.

Design pillars

1. Agent-native - designed for LLM tool calls, not human UIs.
2. Token-efficient - every response is filtered, truncated, and summarized. Full payloads are spilled to disk and referenced by handle.
3. Fast & portable - a Rust core exposed to a thin TypeScript MCP layer via napi-rs.
4. Both ad-hoc and reusable - agents can fire one-off requests or create, save, and re-run declarative collections.